Results 21 to 30 of about 16,806 (262)
Active Zero-Shot Learning [PDF]
Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, 2016 In multi-label classification in the big data age, the number of classes can be in thousands, and obtaining sufficient training data for each class is infeasible. Zero-shot learning aims at predicting a large number of unseen classes using only labeled data from a small set of classes and external knowledge about class relations. However, previous zero-
Sihong Xie, Shaoxiong Wang, Philip S. Yu
openaire +1 more source
Attribute subspaces for zero-shot learning
Pattern Recognition, 2023 Zero-shot learning (ZSL) aims to recognize unseen categories without corresponding training samples, which is a practical yet challenging task in computer vision and pattern recognition community. Current state-of-the-art locality-based ZSL methods aim to learn the explicit locality of discriminative attributes, which may suffer from insufficient class-
Lei Zhou 0008 +6 more
openaire +3 more sources
Applied Sciences, 2019 Traditional supervised learning is dependent on the label of the training data, so there is a limitation that the class label which is not included in the training data cannot be recognized properly.
Sanghyun Seo, Juntae Kim
doaj +1 more source
Practical Aspects of Zero-Shot Learning
, 2022 One of important areas of machine learning research is zero-shot learning. It is applied when properly labeled training data set is not available. A number of zero-shot algorithms have been proposed and experimented with. However, none of them seems to be the "overall winner".
Elie Saad +2 more
openaire +5 more sources
Zero-Shot Compositional Concept Learning [PDF]
Proceedings of the 1st Workshop on Meta Learning and Its Applications to Natural Language Processing, 2021 In this paper, we study the problem of recognizing compositional attribute-object concepts within the zero-shot learning (ZSL) framework. We propose an episode-based cross-attention (EpiCA) network which combines merits of cross-attention mechanism and episode-based training strategy to recognize novel compositional concepts.
Guangyue Xu +2 more
openaire +3 more sources
pLSA-based zero-shot learning [PDF]
2013 IEEE International Conference on Image Processing, 2013 Current zero-shot learning methods relied on attributes to describe the unseen class characteristics, using the learned seen class model. However, these approaches required extensive attribute labels on each object class, and a well-defined, attributes relationship between the seen and unseen class with the aid of human knowledge.
Wai Lam Hoo, Chee Seng Chan
openaire +1 more source
International Journal of Computational Intelligence Systems, 2023 Zero-shot stance detection is both crucial and challenging because it demands detecting the stances of previously unseen targets in the inference stage.
Yu Zhang, Chunling Wang, Jia Wang
doaj +1 more source
Meta-Learning for Generalized Zero-Shot Learning
Proceedings of the AAAI Conference on Artificial Intelligence, 2020 Learning to classify unseen class samples at test time is popularly referred to as zero-shot learning (ZSL). If test samples can be from training (seen) as well as unseen classes, it is a more challenging problem due to the existence of strong bias towards seen classes. This problem is generally known as generalized zero-shot learning (GZSL). Thanks to
Vinay Kumar Verma +2 more
openaire +2 more sources
Zero Shot Learning with the Isoperimetric Loss
Proceedings of the AAAI Conference on Artificial Intelligence, 2020 We introduce the isoperimetric loss as a regularization criterion for learning the map from a visual representation to a semantic embedding, to be used to transfer knowledge to unknown classes in a zero-shot learning setting. We use a pre-trained deep neural network model as a visual representation of image data, a Word2Vec embedding of class labels ...
Shay Deutsch +2 more
openaire +6 more sources
Lvq Treatment for Zero-Shot Learning
SSRN Electronic Journal, 2022 In image classification, there are no labeled training instances for some classes, which are therefore called unseen classes or test classes. To classify these classes, zero-shot learning (ZSL) was developed, which typically attempts to learn a mapping from the (visual) feature space to the semantic space in which the classes are represented by a list ...
openaire +4 more sources